240 lines
10 KiB
Python
240 lines
10 KiB
Python
"""抖音登录二维码元素结构诊断脚本"""
|
|
import asyncio
|
|
import base64
|
|
import json
|
|
import os
|
|
import sys
|
|
|
|
from playwright.async_api import async_playwright
|
|
|
|
ROOT = os.path.dirname(os.path.abspath(__file__))
|
|
PROJECT_ROOT = os.path.dirname(ROOT)
|
|
BROWSERS_PATH = os.path.join(PROJECT_ROOT, "playwright-browsers")
|
|
os.environ.setdefault("PLAYWRIGHT_BROWSERS_PATH", BROWSERS_PATH)
|
|
|
|
OUT_DIR = os.path.join(ROOT, "debug_qr")
|
|
os.makedirs(OUT_DIR, exist_ok=True)
|
|
|
|
|
|
async def inspect():
|
|
async with async_playwright() as p:
|
|
print("launching browser")
|
|
browser = await p.chromium.launch(headless=True)
|
|
context = await browser.new_context(
|
|
viewport={"width": 1280, "height": 900},
|
|
user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
|
)
|
|
page = await context.new_page()
|
|
print("goto douyin.com")
|
|
await page.goto("https://www.douyin.com", wait_until="load")
|
|
await asyncio.sleep(6)
|
|
print("page url:", page.url)
|
|
print("page title:", await page.title())
|
|
|
|
html = await page.content()
|
|
with open(os.path.join(OUT_DIR, "page_initial.html"), "w", encoding="utf-8") as f:
|
|
f.write(html)
|
|
print("saved page_initial.html")
|
|
|
|
# 点击登录按钮，触发登录弹窗
|
|
login_clicked = False
|
|
for sel in ["text=登录", "text=登录/注册", "text=立即登录", "button:has-text('登录')", "[class*='login']", "[class*='Login']"]:
|
|
try:
|
|
el = await page.wait_for_selector(sel, timeout=3000)
|
|
if el:
|
|
await el.click()
|
|
print("clicked via selector:", sel)
|
|
login_clicked = True
|
|
break
|
|
except Exception as e:
|
|
print(f"selector {sel} failed: {e}")
|
|
if not login_clicked:
|
|
for attempt in range(3):
|
|
try:
|
|
clicked = await page.evaluate("""() => {
|
|
const nodes = [...document.querySelectorAll('button, span, div, a, p')];
|
|
for (const el of nodes) {
|
|
const t = (el.innerText || '').trim();
|
|
if ((t.includes('登录') || t.toLowerCase().includes('login')) && el.offsetParent) {
|
|
el.click();
|
|
return t;
|
|
}
|
|
}
|
|
return '';
|
|
}""")
|
|
print("clicked via js:", clicked)
|
|
if clicked:
|
|
break
|
|
except Exception as e:
|
|
print(f"js click attempt {attempt} err: {e}")
|
|
await asyncio.sleep(1)
|
|
await asyncio.sleep(4)
|
|
|
|
html = await page.content()
|
|
with open(os.path.join(OUT_DIR, "page_after_login_click.html"), "w", encoding="utf-8") as f:
|
|
f.write(html)
|
|
print("saved page_after_login_click.html")
|
|
|
|
try:
|
|
await page.screenshot(path=os.path.join(OUT_DIR, "00_viewport.png"), full_page=False, timeout=10000)
|
|
print("saved 00_viewport.png")
|
|
except Exception as e:
|
|
print("viewport screenshot failed:", e)
|
|
|
|
# 尝试切换「扫码登录」
|
|
for frame in page.frames:
|
|
try:
|
|
switched = await frame.evaluate("""() => {
|
|
const nodes = [...document.querySelectorAll('span, div, a, button, p')];
|
|
let best = null;
|
|
for (const el of nodes) {
|
|
const t = (el.innerText || '').trim();
|
|
if ((t === '扫码登录' || t === '扫码') && el.offsetParent) {
|
|
if (!best || el.children.length < best.children.length) best = el;
|
|
}
|
|
}
|
|
if (best) { best.click(); return 'switched'; }
|
|
return '';
|
|
}""")
|
|
print(f"frame {frame.url[:60]} switched={switched}")
|
|
except Exception as e:
|
|
print(f"frame switch err: {e}")
|
|
await asyncio.sleep(2)
|
|
|
|
report = {"frames": [], "candidates": []}
|
|
|
|
# 遍历所有 frame，查找二维码相关元素
|
|
for idx, frame in enumerate(page.frames):
|
|
frame_report = {"index": idx, "url": frame.url, "qrcodes": [], "panels": []}
|
|
selectors = [
|
|
"[class*='qrcode'] img",
|
|
"[class*='QrCode'] img",
|
|
"[class*='qr-code'] img",
|
|
"img[class*='qrcode']",
|
|
"img[src*='qrcode']",
|
|
"img[alt*='二维码']",
|
|
"img[alt*='qr']",
|
|
"[class*='qrcode'] canvas",
|
|
"canvas[class*='qrcode']",
|
|
"[class*='scan'] img",
|
|
"[class*='scan'] canvas",
|
|
"img",
|
|
"canvas",
|
|
]
|
|
for sel in selectors:
|
|
try:
|
|
els = await frame.query_selector_all(sel)
|
|
for el in els:
|
|
try:
|
|
visible = await el.is_visible()
|
|
box = await el.bounding_box()
|
|
tag = await el.evaluate("e => e.tagName")
|
|
src = await el.get_attribute("src") or ""
|
|
alt = await el.get_attribute("alt") or ""
|
|
cls = await el.get_attribute("class") or ""
|
|
outer = await el.evaluate("e => e.outerHTML.slice(0, 300)")
|
|
info = {
|
|
"selector": sel,
|
|
"tag": tag,
|
|
"visible": visible,
|
|
"box": box,
|
|
"src_prefix": src[:120] if src else "",
|
|
"alt": alt,
|
|
"class": cls,
|
|
"outer": outer,
|
|
}
|
|
if (tag.lower() in ("img", "canvas") and box and box.get("width", 0) > 40 and visible):
|
|
frame_report["qrcodes"].append(info)
|
|
# 截图该元素
|
|
safe_name = f"frame{idx}_{tag}_{int(box['x'])}_{int(box['y'])}.png"
|
|
try:
|
|
await el.screenshot(path=os.path.join(OUT_DIR, safe_name))
|
|
info["screenshot"] = safe_name
|
|
except Exception as e:
|
|
info["screenshot_err"] = str(e)
|
|
except Exception as e:
|
|
print(f" el inspect err: {e}")
|
|
except Exception as e:
|
|
print(f"frame {idx} selector {sel} err: {e}")
|
|
|
|
# 登录面板/容器
|
|
panel_selectors = [
|
|
"[class*='qrcode-container']",
|
|
"[class*='qrcodeContainer']",
|
|
"[class*='qrcode']",
|
|
"[class*='QrCode']",
|
|
"[class*='login-scan']",
|
|
"[class*='scan-code']",
|
|
"#login-pannel",
|
|
"[class*='login_panel']",
|
|
"[class*='login-panel']",
|
|
"[class*='account_login']",
|
|
]
|
|
for sel in panel_selectors:
|
|
try:
|
|
els = await frame.query_selector_all(sel)
|
|
for el in els:
|
|
visible = await el.is_visible()
|
|
box = await el.bounding_box()
|
|
cls = await el.get_attribute("class") or ""
|
|
if visible and box and box.get("width", 0) > 80:
|
|
frame_report["panels"].append({
|
|
"selector": sel,
|
|
"class": cls,
|
|
"box": box,
|
|
})
|
|
safe_name = f"frame{idx}_panel_{int(box['x'])}_{int(box['y'])}.png"
|
|
try:
|
|
await el.screenshot(path=os.path.join(OUT_DIR, safe_name))
|
|
frame_report["panels"][-1]["screenshot"] = safe_name
|
|
except Exception as e:
|
|
frame_report["panels"][-1]["screenshot_err"] = str(e)
|
|
except Exception as e:
|
|
pass
|
|
|
|
report["frames"].append(frame_report)
|
|
|
|
# 尝试用 JS 暴力查找所有 img/canvas 中可能为二维码的
|
|
all_candidates = await page.evaluate("""() => {
|
|
const out = [];
|
|
document.querySelectorAll('img, canvas').forEach((el, i) => {
|
|
const rect = el.getBoundingClientRect();
|
|
if (rect.width > 30 && rect.height > 30 && rect.width < 600 && rect.height < 600) {
|
|
const style = window.getComputedStyle(el);
|
|
out.push({
|
|
tag: el.tagName,
|
|
index: i,
|
|
width: rect.width,
|
|
height: rect.height,
|
|
x: rect.x,
|
|
y: rect.y,
|
|
src: el.tagName === 'IMG' ? (el.src || '').slice(0, 200) : '',
|
|
alt: el.alt || '',
|
|
class: el.className || '',
|
|
parentText: (el.parentElement ? el.parentElement.innerText : '').slice(0, 80),
|
|
});
|
|
}
|
|
});
|
|
return out;
|
|
}""")
|
|
report["candidates"] = all_candidates
|
|
|
|
with open(os.path.join(OUT_DIR, "report.json"), "w", encoding="utf-8") as f:
|
|
json.dump(report, f, ensure_ascii=False, indent=2)
|
|
|
|
print("report saved to", os.path.join(OUT_DIR, "report.json"))
|
|
print("found qrcode-like elements:", sum(len(f["qrcodes"]) for f in report["frames"]))
|
|
print("found panels:", sum(len(f["panels"]) for f in report["frames"]))
|
|
|
|
await browser.close()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
try:
|
|
asyncio.run(inspect())
|
|
except Exception as e:
|
|
print("FATAL:", e, file=sys.stderr)
|
|
import traceback
|
|
traceback.print_exc()
|
|
raise
|